Automatic and Accurate Conflation of Different Road-Network Vector Data towards Multi-Modal Navigation

Abstract

Abstract:With the rapid improvement of geospatial data acquisition and processing techniques, a variety of geospatial databases from public or private organizations have become available. Quite often, one dataset may be superior to other datasets in one, but not all aspects. In Germany, for instance, there were three major road network vector data, viz. Tele Atlas (which is now "TOMTOM"), NAVTEQ (which is now "here"), and ATKIS. However, none of them was qualified for the purpose of multi-modal navigation (e.g., driving + walking): Tele Atlas and NAVTEQ consist of comprehensive routing-relevant information, but many pedestrian ways are missing; ATKIS covers more pedestrian areas but the road objects are not fully attributed. To satisfy the requirements of multi-modal navigation, an automatic approach has been proposed to conflate different road networks together, which involves five routines: (a) road-network matching between datasets; (b) identification of the pedestrian ways; (c) geometric transformation to eliminate geometric inconsistency; (d) topologic remodeling of the conflated road network; and (e) error checking and correction. The proposed approach demonstrates high performance in a number of large test areas and therefore has been successfully utilized for the real-world data production in the whole region of Germany. As a result, the conflated road network allows the multi-modal navigation of "driving + walking".

Automatically Building Linking Relations between Lane-Level Map and Commercial Navigation Map Using Topological Networks Matching

“…Generally, the networks to be matched are preprocessed to build specific structures to pave the way for network matching (Volz, 2006; Mustière and Devogele, 2008; Abdolmajidi et al, 2015; Zhang et al, 2016). In this paper, topology reconstruction is performed initially to eliminate the topological inconsistencies between CNM and LLM.…”

Measuring conflation success

“…Steps taken to perform a road network conflation process to allow multi-modal navigation. From Zhang et al (2016).…”

Measuring conflation success

“…For them, percentage metrics were used to report conflation success. They can be applied to point features (Chen et al, 2004), line features (Zhang et al, 2016, Chen et al, 2006, Chen et al, 2008, Yang et al, 2012 and polygon features (Sledge et al, 2011). As usual, in order to apply these metrics, it is needed to have a ground truth set of features (reference features) to which the conflated dataset will be compared.…”

“…However, some scores are lower (around 80-85%), due to a segmentation fail to find buildings, hidden by trees or shades, which is another issue to take into account when working with automatically vector extractions. Zhang et al (2016) performs a road network conflation process to allow multimodal navigation. Their process is shown in Figure 2 and involves five steps: (1) road-network matching between datasets; (2) identification of the pedestrian ways;…”

“…In this case, one of the differences with Zhang et al (2016) is that they compute these metrics using the length of the roads instead of counting the features. They conduct several experiments, using two different datasets: orthoimagery (0.3 m/pixel and 1 m/pixel resolution) and vector data.…”